© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 11402
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns and specific phrases indicating notable observations or insights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "That" followed by a reporting verb

    np_acts-logits-general · gemini-2.0-flash

    that said

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.75
    providedIn
    -0.55
    CodeAttribute
    -0.54
    агности
    -0.51
    zarchiwizowane
    -0.49
    商品説明
    -0.48
    WebElementEntity
    -0.48
    RenderAtEndOf
    -0.48
    abcdefghijklmnop
    -0.47
    onsored
    -0.47
    POSITIVE LOGITS
     aside
    0.73
     gezegd
    0.70
    said
    0.67
     being
    0.67
     begs
    0.65
     notwithstanding
    0.65
     SAID
    0.63
    SourceChecksum
    0.63
    رشف
    0.62
     BEING
    0.61
    Activations Density 0.090%

    No Known Activations